Question answering method for query information, and related apparatus

Abstract

The present disclosure provides a question answering method and apparatus for query information. The method may include: receiving query information input by a user, and analyzing a query target comprised in the query information; recalling candidate answers from a pre-generated knowledge graph based on the query target, where the knowledge graph is constructed based on inherent data in a map database and dynamic data of historical users, and the dynamic data includes at least one of comment data, search data, or spatiotemporal big data; and returning, in response to that there is a target answer whose matching degree with the query target exceeds a preset threshold in the candidate answers, the target answer to the user.

What is claimed is: 
     
       1. A question answering method for query information, comprising:
 receiving query information input by a user, and analyzing a query target included in the query information; 
 recalling candidate answers from a pre-generated knowledge graph based on the query target, wherein the pre-generated knowledge graph is constructed on the server based on inherent data in a map database and dynamic data of historical users, and the dynamic data comprises at least one of comment data, search data, or spatiotemporal big data; and 
 returning, in response to that there is a target answer whose matching degree with the query target exceeds a preset threshold in the candidate answers, the target answer to the user, 
 wherein the method further comprises:
 generating, in response to the same query target being input by a plurality of different historical users within a preset period respectively, recommendation information based on the query target and the target answer; 
 obtaining a number of query targets corresponding to each piece of the recommendation information, and generating popularity information of each piece of the recommendation information; and 
 sorting each piece of the recommendation information based on the popularity information, and pushing each piece of the recommendation information sequentially to the user according to a sorting result. 
 
 
     
     
       2. The method according to  claim 1 , wherein the method further comprises:
 pushing, in response to that there is no target answer whose matching degree with the query target exceeds the preset threshold in the candidate answers, the query information to an expert user; and 
 returning a recommended answer returned by the expert user based on the query information to the user. 
 
     
     
       3. The method according to  claim 2 , wherein the method further comprises:
 adding the recommended answer to the pre-generated knowledge graph corresponding to the query target. 
 
     
     
       4. The method according to  claim 1 , wherein the pre-generated knowledge graph is constructed by:
 extracting inherent data of each target object from a map database, wherein the inherent data comprises at least one of: contact numbers, business hours, geographic coordinates, or an industry of each target object; 
 generating a first knowledge graph corresponding to each target object using the inherent data corresponding to each target object; 
 adding dynamic data nodes of at least one information type to each first knowledge graph; 
 obtaining dynamic data corresponding to each target object, and extracting associated information from each piece of the dynamic data based on an information type, wherein content included in the associated information is related to the information type; and 
 adding the information type corresponding to the associated information to each first knowledge graph to generate a second knowledge graph. 
 
     
     
       5. The method according to  claim 4 , wherein the method further comprises:
 obtaining keyword information corresponding to each of the dynamic data nodes; and 
 wherein extracting associated information from each piece of the dynamic data based on the information type, comprises:
 performing word segmentation process on each piece of the dynamic data; and 
 extracting, in response to that a word segmentation result of the dynamic data comprises the keyword information, the dynamic data as the associated information of the information type of the dynamic data nodes corresponding to the keyword information. 
 
 
     
     
       6. The method according to  claim 4 , wherein the method further comprises:
 determining the information type of the dynamic data nodes based on an information type of query information of the historical users. 
 
     
     
       7. An electronic device, comprising:
 at least one processor; and 
 a memory communicatively connected to the at least one processor and configured to store instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising: 
 receiving an input of query information by a user, and analyzing a query target included in the query information; 
 recalling candidate answers from a pre-generated knowledge graph based on the query target, wherein the pre-generated knowledge graph is constructed on the server based on inherent data in a map database and dynamic data of historical users, and the dynamic data comprises at least one of comment data, search data, or spatiotemporal big data; and 
 returning, in response to that there is a target answer whose matching degree with the query target exceeds a preset threshold in the candidate answers, the target answer to the user, 
 wherein the operations further comprise:
 generating, in response to the same query target being input by a plurality of different historical users within a preset period respectively, recommendation information based on the query target and the target answer; 
 obtaining a number of query targets corresponding to each piece of the recommendation information, and generating popularity information of each piece of the recommendation information; and 
 sorting each piece of the recommendation information based on the popularity information, and pushing each piece of the recommendation information sequentially to the user according to a sorting result. 
 
 
     
     
       8. The electronic device according to  claim 7 , wherein the operations further comprise:
 pushing, in response to that there is no target answer whose matching degree with the query target exceeds the preset threshold in the candidate answers, the query information to an expert user; and 
 returning a recommended answer returned by the expert user based on the query information to the user. 
 
     
     
       9. The electronic device according to  claim 8 , wherein the operations further comprise:
 adding the recommended answer to the pre-generated knowledge graph corresponding to the query target. 
 
     
     
       10. The electronic device according to  claim 7 , wherein the pre-generated knowledge graph is constructed by:
 extracting inherent data of each target object from a map database, wherein the inherent data comprises at least one of: contact numbers, business hours, geographic coordinates, or an industry of each target object; 
 generating a first knowledge graph corresponding to each target object using the inherent data corresponding to each target object; 
 adding dynamic data nodes of at least one information type to each first knowledge graph; 
 obtaining dynamic data corresponding to each target object, and extracting associated information from each piece of the dynamic data based on an information type, wherein content included in the associated information is related to the information type; and 
 adding the information type corresponding to the associated information to each first knowledge graph to generate a second knowledge graph. 
 
     
     
       11. A non-transitory computer readable storage medium storing computer instructions, wherein, the computer instructions are used to cause a computer to perform the question answering method for query information according to  claim 1 . 
     
     
       12. The electronic device according to  claim 10 , wherein the operations further comprise:
 obtaining keyword information corresponding to each of the dynamic data nodes; and 
 wherein extracting associated information from each piece of the dynamic data based on the information type, comprises:
 performing word segmentation process on each piece of the dynamic data; and 
 extracting, in response to that a word segmentation result of the dynamic data comprises the keyword information, the dynamic data as the associated information of the information type of the dynamic data nodes corresponding to the keyword information. 
 
 
     
     
       13. The electronic device according to  claim 10 , wherein the operations further comprise:
 determining the information type of the dynamic data nodes based on an information type of query information of the historical users.